On Wed, Oct 14, 2026 at 03:51:27PM +0200, Geert Uytterhoeven wrote: > On Tue, 13 Oct 2026 at 05:49, Kees Cook <[email protected]> wrote: > > I was expecting this to appear under Documentation/. The agents are > > designed to read human text, so let's make it at least passingly > > sensible for humans to read too. :) > > The expectation is that the agents are becoming better in understanding, > so more "instructions" can be shared?
Exactly. And the rate of frontier model improvement has me convinced that there is no need to spend any time writing documentation to be consumed _only_ by the agents. If an agent gets it wrong after reading our existing documentation, ask it what would need to change for it to understand it, and then see if that makes it better for a human too, and send those patches. :) -- Kees Cook
